---
tags:
- autotrain
- text-generation-inference
- text-generation
- peft
- mlx
library_name: transformers
base_model: ben-at-jorah/emergency-llama32-1b-finetune-rmsys3
widget:
- messages:
  - role: user
    content: What is your favorite condiment?
license: other
datasets:
- ben-at-jorah/emergency-training-data_2024-11-20
---

# ben-at-jorah/emergency-llama32-1b-finetune-rmsys3_mlx-8bit

The Model [ben-at-jorah/emergency-llama32-1b-finetune-rmsys3_mlx-8bit](https://huggingface.co/ben-at-jorah/emergency-llama32-1b-finetune-rmsys3_mlx-8bit) was converted to MLX format from [ben-at-jorah/emergency-llama32-1b-finetune-rmsys3](https://huggingface.co/ben-at-jorah/emergency-llama32-1b-finetune-rmsys3) using mlx-lm version **0.19.2**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("ben-at-jorah/emergency-llama32-1b-finetune-rmsys3_mlx-8bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```